Group delay functions for speaker diarization

Yadav, Mohit; Sao, Anil Kumar; Dileep, A. D.; Rajan, P.K.

doi:10.1109/ncc.2016.7561127

Cited by 3 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the focus of this work is towards different frameworks, we used standard MFCC in all our experiments. However, other spectral features like MFS and LFS [8] [14], and group delay based features [15] can also be used in the proposed architectures. The proposed systems are generic enough to be used along with deep embeddings instead of standard spectral features.…”

Section: Discussionmentioning

confidence: 99%

“…The Mel Filterbank Slope (MFS) features and Linear Filterbank Slope (LFS) features have been shown to be better at speaker discrimination in comparison to MFCC features, owing to the emphasis of higher order formants [14]. Group delay based features have also shown to be better at speaker discrimination over traditional MFCC [15]. The i-vector based approaches have been used to build better speaker models [16], [17].…”

Section: Approaches To Speaker Diarizationmentioning

confidence: 99%

See 1 more Smart Citation

Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings

Dawalatabad,

Madikeri,

Sekhar

et al. 2020

Preprint

View full text Add to dashboard Cite

Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly distributing speaker information across the initial segments, and (ii) incorporating speaker discriminative features within the unsupervised diarization framework. In the first part of the work, a varying length segment initialization technique for Information Bottleneck (IB) based speaker diarization system using phoneme rate as the side information is proposed. This initialization distributes speaker information uniformly across the segments and provides a better starting point for IB based clustering. In the second part of the work, we present a Two-Pass Information Bottleneck (TPIB) based speaker diarization system that incorporates speaker discriminative features during the process of diarization. The TPIB based speaker diarization system has shown improvement over the baseline IB based system. During the first pass of the TPIB system, a coarse segmentation is performed using IB based clustering. The alignments obtained are used to generate speaker discriminative features using a shallow feed-forward neural network and linear discriminant analysis. The discriminative features obtained are used in the second pass to obtain the final speaker boundaries. In the final part of the paper, variable segment initialization is combined with the TPIB framework. This leverages the advantages of better segment initialization and speaker discriminative features that results in an additional improvement in performance. An evaluation on standard meeting datasets shows that a significant absolute improvement of 3.9% and 4.7% is obtained on the NIST and AMI datasets, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%